Skills Guide

PDF to Markdown

VerifiedCaution

Convert a PDF into high-quality Markdown using the MinerU API VLM pipeline. Supports OCR, paper text extraction, and image extraction.

Sby Skills Guide Bot
Data & AIBeginner
007/27/2026
Claude Code
#pdf#markdown#conversion#mineru#vlm

Recommended for

Claude CodeData scientistData & analysis

Our review

Converts a PDF to high-quality Markdown using the MinerU API VLM pipeline for accurate extraction of formulas, tables, and complex layouts.

Strengths

  • High conversion quality for academic PDFs
  • Extracts embedded images
  • Handles complex formulas and tables
  • Supports language hints for better accuracy

Limitations

  • Requires a MinerU API token
  • Depends on internet connectivity
  • Overwrites existing files without warning
When to use it

Use this skill when you need to convert academic or technical PDFs to Markdown with high fidelity, especially for formulas and tables.

When not to use it

Avoid this skill when working offline, without an API token, or when only plain text extraction is needed.

Security analysis

Caution
Quality score85/100

The skill invokes a Python script that sends the PDF to the MinerU API for processing. This involves network communication and potential data exfiltration risk. However, the script is not provided, so no malicious code is evident. The environment variable token handling is standard. The operation is legitimate for PDF conversion.

Findings
  • •Sends PDF files to an external API, which may expose sensitive content if not careful with token and endpoint.

Examples

Convert PDF to Markdown
Convert this PDF to Markdown: /path/to/paper.pdf
Convert with language hint
Convert this Chinese PDF to Markdown: /path/to/chinese_paper.pdf -l ch

name: pdf-to-md description: > Convert a PDF into high-quality Markdown through the MinerU API VLM pipeline. Use this skill whenever the user wants PDF-to-Markdown conversion, OCR-like extraction, paper text extraction, or Markdown plus extracted images from a PDF. This skill supports the API backend only and always uses the high-quality VLM model configuration. argument-hint: "<pdf_path> [-l lang]" allowed-tools: Bash

PDF to Markdown

Converts a PDF to:

<pdf_stem>.md
<pdf_stem>_images/

Prerequisite

Set the MinerU API token:

export MINERU_API_TOKEN="your_token_here"

Usage

python3 "${SKILL_DIR}/scripts/mineru-api.py" <pdf_path> [-l lang]
  • pdf_path: local PDF path
  • -l lang: language hint, en or ch

Backend contract

  • Supported backend: MinerU API only
  • Model: VLM
  • Goal: highest available parsing quality for formulas, tables, and mixed-layout academic PDFs

Output behavior

  • Output files are written next to the PDF
  • Existing Markdown and image directories for the same stem may be overwritten
  • Example: paper.pdf -> paper.md and paper_images/
Related skills

Prompt Engineering

Data & AI

Prompt engineering best practices and templates to maximize AI outputs.

claudeCursorWindsurf+1beginner
289
78
869
Admin

Data Visualization

Data & AI

Generates data visualizations and charts tailored to your data.

claudeCursorWindsurfintermediate
198
56
705
Admin

RAG Architecture Setup

Data & AI

Setup guide for RAG (Retrieval-Augmented Generation) architectures.

claudeCursorWindsurfadvanced
167
51
667
Admin